{"id":"https://openalex.org/W3015484572","doi":"https://doi.org/10.1109/icassp40776.2020.9053399","title":"An Empirical Study of Transformer-Based Neural Language Model Adaptation","display_name":"An Empirical Study of Transformer-Based Neural Language Model Adaptation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015484572","doi":"https://doi.org/10.1109/icassp40776.2020.9053399","mag":"3015484572"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100343450","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-7200-4244"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ke Li","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068582966","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0002-8300-1855"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051747323","display_name":"Tianxing He","orcid":"https://orcid.org/0009-0008-6383-0307"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianxing He","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028860597","display_name":"Hongzhao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzhao Huang","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047400593","display_name":"Fuchun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuchun Peng","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100343450"],"corresponding_institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":3.0489,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92834705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"7934","last_page":"7938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7979311943054199},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7779603004455566},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6815874576568604},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5909666419029236},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5867085456848145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49354350566864014},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.49113747477531433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46006739139556885},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42166972160339355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3379819393157959},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3208986222743988},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2854042649269104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09235578775405884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979311943054199},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7779603004455566},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6815874576568604},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5909666419029236},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5867085456848145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49354350566864014},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.49113747477531433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46006739139556885},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42166972160339355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3379819393157959},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3208986222743988},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2854042649269104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09235578775405884},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W182840523","https://openalex.org/W1494108583","https://openalex.org/W1524333225","https://openalex.org/W1999965501","https://openalex.org/W2020073413","https://openalex.org/W2064675550","https://openalex.org/W2072223048","https://openalex.org/W2095848329","https://openalex.org/W2111305191","https://openalex.org/W2127836646","https://openalex.org/W2138857742","https://openalex.org/W2399550240","https://openalex.org/W2513257850","https://openalex.org/W2514741789","https://openalex.org/W2555428947","https://openalex.org/W2747236259","https://openalex.org/W2748092010","https://openalex.org/W2802201485","https://openalex.org/W2888867175","https://openalex.org/W2889152503","https://openalex.org/W2891628540","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2940131043","https://openalex.org/W2943845043","https://openalex.org/W2948975009","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W4385245566","https://openalex.org/W6607455302","https://openalex.org/W6631362777","https://openalex.org/W6674367285","https://openalex.org/W6712868603","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501","https://openalex.org/W2964413124"],"abstract_inverted_index":{"We":[0,77],"explore":[1],"two":[2,80],"adaptation":[3],"approaches":[4,81],"of":[5,55],"deep":[6],"Transformer":[7,29],"based":[8],"neural":[9],"language":[10],"models":[11,58],"(LMs)":[12],"for":[13],"automatic":[14],"speech":[15],"recognition.":[16],"The":[17,49,136],"first":[18,26],"approach":[19,51,123,150],"is":[20,52],"a":[21,28,32,53,152],"pretrain-finetune":[22],"framework,":[23],"where":[24],"we":[25],"pretrain":[27],"LM":[30],"on":[31,63,94,133],"large-scale":[33],"text":[34],"corpus":[35],"from":[36],"scratch":[37],"and":[38,65,90,97,113,120,129,143],"then":[39],"adapt":[40],"it":[41],"to":[42,69,126],"relatively":[43],"small":[44],"target":[45,66],"domains":[46],"via":[47],"finetuning.":[48,114],"second":[50],"mixer":[54,106,122,137,149],"dynamically":[56],"weighted":[57],"that":[59,104],"are":[60],"separately":[61],"trained":[62],"source":[64],"domains,":[67],"aiming":[68],"improve":[70],"simple":[71,91],"linear":[72,141],"interpolation":[73,92,142],"with":[74,82,116],"dynamic":[75],"weighting.":[76],"compare":[78],"the":[79,105,121,148],"three":[83],"baselines":[84,112],"-":[85,93],"without":[86],"adaptation,":[87,118],"merging":[88,144],"data,":[89],"Switchboard":[95],"(SWBD)":[96],"Wall":[98],"Street":[99],"Journal":[100],"(WSJ).":[101],"Experiments":[102],"show":[103],"model":[107,138],"generally":[108],"performs":[109],"better":[110],"than":[111],"Compared":[115],"no":[117],"finetuning":[119],"obtain":[124],"up":[125],"relative":[127],"11.5%":[128],"14.1%":[130],"WER":[131,155],"reductions":[132],"SWBD,":[134],"respectively.":[135],"also":[139],"outperforms":[140],"data.":[145],"On":[146],"WSJ,":[147],"achieves":[151],"new":[153],"state-of-the-art":[154],"result.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}